Autonomous Commit and Commit Causality Clocks: Building Blocks for Logging and Recovery on Modern Hardware

Traditional ARIES has long been the standard for logging and recovery in database systems. Yet, its overhead limits system efficiency on modern hardware, leading to a shift towards decentralized logging for improved performance and scalability. Decentralized logging, however, poses two major challenges: (1) its integration with existing commit processing protocols fails to provide low-latency commits, (2) current variants introduce many critical trade-offs that hinder widespread adoption. This paper aims to address these gaps. To tackle the first issue, we introduce Autonomous Commit , the first commit protocol that fully utilizes modern NVMe SSDs to achieve low-latency durable commits with decentralized logging. Second, we propose Commit Causality Clocks , a new dependency tracking mechanism optimized for decentralized logging that retains the strengths of existing approaches while eliminating their limitations. We also revisit the recovery subsystem, enabling DBMS logging to work directly on block devices for optimal performance during normal operation. Our experimental evaluation demonstrates that these techniques together deliver very good scalability and low-latency durable commits across diverse workloads, enabling a high-performance logging and recovery design.